© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21530
    Prev
    Next
    INDEX
    Explanations

    variable assignment in conditional

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is keyed to recognize variable‐name tokens (e.g. identifiers or template placeholders) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    -2.36
    ucción
    -1.54
    
    -1.53
    vertida
    -1.52
    </h5>
    -1.52
    ")]
    -1.41
    chial
    -1.40
    НИЙ
    -1.40
     I
    -1.39
    produtos
    -1.39
    POSITIVE LOGITS
    してから
    1.79
     ketika
    1.73
    うれ
    1.69
    Interestingly
    1.66
     Когда
    1.62
    When
    1.59
     When
    1.58
    気持ちを
    1.58
     shouldBe
    1.55
    したのが
    1.54
    Activations Density 0.050%

    No Known Activations